laxuu/transformer_vqa
Updated
Laxmi Tiwari
laxuu
AI & ML interests
Agentic AI, RL, MARL
Recent Activity
reacted to theirpost with 👍 3 days ago
Hot take :Wednesday🔥
For years, AI progress has often looked like:
"Need a smarter model?"
➡️ Add more parameters.
➡️ Add more GPUs.
➡️ Hope your budget survives.
RobotxR1 explores a different idea: what if intelligence comes from experience rather than scale?
Instead of relying solely on massive pretraining, it combines LLMs with reinforcement learning, allowing models to learn through interaction, feedback, and mistakes.
As someone interested in Recurrent RL and autonomous systems, this raises an exciting question:
Are we entering the era where experience becomes more valuable than parameters?
The next breakthrough AI might not be the biggest model.
It might be the one that learns continuously.
📄 Paper: https://arxiv.org/pdf/2505.03238
💻 Code: https://github.com/ForzaETH/LLMxRobot/tree/main
#ReinforcementLearning #LLM #Robotics #AI #smallmodelhackathonhuggingface
reacted to theirpost with 🧠 3 days ago
Hot take :Wednesday🔥
For years, AI progress has often looked like:
"Need a smarter model?"
➡️ Add more parameters.
➡️ Add more GPUs.
➡️ Hope your budget survives.
RobotxR1 explores a different idea: what if intelligence comes from experience rather than scale?
Instead of relying solely on massive pretraining, it combines LLMs with reinforcement learning, allowing models to learn through interaction, feedback, and mistakes.
As someone interested in Recurrent RL and autonomous systems, this raises an exciting question:
Are we entering the era where experience becomes more valuable than parameters?
The next breakthrough AI might not be the biggest model.
It might be the one that learns continuously.
📄 Paper: https://arxiv.org/pdf/2505.03238
💻 Code: https://github.com/ForzaETH/LLMxRobot/tree/main
#ReinforcementLearning #LLM #Robotics #AI #smallmodelhackathonhuggingface
reacted to theirpost with 🚀 3 days ago
Hot take :Wednesday🔥
For years, AI progress has often looked like:
"Need a smarter model?"
➡️ Add more parameters.
➡️ Add more GPUs.
➡️ Hope your budget survives.
RobotxR1 explores a different idea: what if intelligence comes from experience rather than scale?
Instead of relying solely on massive pretraining, it combines LLMs with reinforcement learning, allowing models to learn through interaction, feedback, and mistakes.
As someone interested in Recurrent RL and autonomous systems, this raises an exciting question:
Are we entering the era where experience becomes more valuable than parameters?
The next breakthrough AI might not be the biggest model.
It might be the one that learns continuously.
📄 Paper: https://arxiv.org/pdf/2505.03238
💻 Code: https://github.com/ForzaETH/LLMxRobot/tree/main
#ReinforcementLearning #LLM #Robotics #AI #smallmodelhackathonhuggingface
Organizations
laxuu/Florence-2-vqa_final
Image-Text-to-Text • 0.3B • Updated
laxuu/Florence-2-vqa_demo
Image-Text-to-Text • 0.3B • Updated
laxuu/Florence-2-vqa
Image-Text-to-Text • 0.3B • Updated
laxuu/Taxi-v3
Reinforcement Learning • Updated
laxuu/q-FrozenLake-v1-4x4-noSlippery
Reinforcement Learning • Updated
laxuu/ppo-LunarLander-v2-1
Reinforcement Learning • Updated
laxuu/ppo_model
Updated
laxuu/ppo-LunarLander-v2
Reinforcement Learning • Updated